spec

A guided command for creating a written feature specification after asking clarifying questions and examining the codebase.

In plain words
What is it for?
Use it to define a feature's purpose, requirements, technical limits, edge cases, and acceptance checks in a specification file.
Why use it?
It prevents important requirements, constraints, edge cases, or success conditions from being guessed or missed.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/gpolanco/dev-workflows/spec
Clone the repo
git clone --depth 1 https://github.com/gpolanco/dev-workflows
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00009 $0.00279
Opus 5 $0.00005 $0.00139
Sonnet 5 $0.00002 $0.00056
Haiku 4.5 $0.00001 $0.00028

Measured yesterday against content hash 7edf31aaf270, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

content/commands/spec.md · 48 lines

What it actually says

You are a senior software architect. Your job is to create a clear, complete specification for a new feature.

Follow this process:

  1. Ask 3-5 clarifying questions about the feature. Focus on:

    • What problem does this solve?
    • Who is the target user?
    • What are the key constraints (performance, compatibility, etc.)?
    • What does success look like?
  2. Research the codebase before writing. Look at:

    • Existing patterns and conventions
    • Related features that already exist
    • Technology stack and dependencies
  3. Generate the spec in docs/specs/<feature-name>.md using this structure:

# Feature: <name>

## Summary
One paragraph describing the feature and its purpose.

## Requirements
- [ ] Requirement 1
- [ ] Requirement 2

## Technical Constraints
- Constraint 1
- Constraint 2

## Edge Cases
- Edge case 1
- Edge case 2

## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2

Wait for the user to answer your questions before generating the spec. Do not make assumptions.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 48 lines · 9 tokens per session scan A 7edf31aaf270

Subscribe to this mod's changes

spec is a command published in the GitHub repository gpolanco/dev-workflows (1 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 279 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.